netfilter: kill the fake untracked conntrack objects

resurrect an old patch from Pablo Neira to remove the untracked objects.

Currently, there are four possible states of an skb wrt. conntrack.

1. No conntrack attached, ct is NULL.
2. Normal (kmem cache allocated) ct attached.
3. a template (kmalloc'd), not in any hash tables at any point in time
4. the 'untracked' conntrack, a percpu nf_conn object, tagged via
   IPS_UNTRACKED_BIT in ct->status.

Untracked is supposed to be identical to case 1.  It exists only
so users can check

-m conntrack --ctstate UNTRACKED vs.
-m conntrack --ctstate INVALID

e.g. attempts to set connmark on INVALID or UNTRACKED conntracks is
supposed to be a no-op.

Thus currently we need to check
 ct == NULL || nf_ct_is_untracked(ct)

in a lot of places in order to avoid altering untracked objects.

The other consequence of the percpu untracked object is that all
-j NOTRACK (and, later, kfree_skb of such skbs) result in an atomic op
(inc/dec the untracked conntracks refcount).

This adds a new kernel-private ctinfo state, IP_CT_UNTRACKED, to
make the distinction instead.

The (few) places that care about packet invalid (ct is NULL) vs.
packet untracked now need to test ct == NULL vs. ctinfo == IP_CT_UNTRACKED,
but all other places can omit the nf_ct_is_untracked() check.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

3 files changed, 6 insertions, 16 deletions

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 8a4a57b887fb..9a75d9933e63 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1556,12 +1556,8 @@ static inline void ip_vs_notrack(struct sk_buff *skb)
 	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
 
 	if (!ct || !nf_ct_is_untracked(ct)) {
-		struct nf_conn *untracked;
-
 		nf_conntrack_put(&ct->ct_general);
-		untracked = nf_ct_untracked_get();
-		nf_conntrack_get(&untracked->ct_general);
-		nf_ct_set(skb, untracked, IP_CT_NEW);
+		nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
 	}
 #endif
 }
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 19605878da47..012b99f563e5 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -243,14 +243,6 @@ extern s32 (*nf_ct_nat_offset)(const struct nf_conn *ct,
 			       enum ip_conntrack_dir dir,
 			       u32 seq);
 
-/* Fake conntrack entry for untracked connections */
-DECLARE_PER_CPU_ALIGNED(struct nf_conn, nf_conntrack_untracked);
-static inline struct nf_conn *nf_ct_untracked_get(void)
-{
-	return raw_cpu_ptr(&nf_conntrack_untracked);
-}
-void nf_ct_untracked_status_or(unsigned long bits);
-
 /* Iterate over all conntracks: if iter returns true, it's deleted. */
 void nf_ct_iterate_cleanup(struct net *net,
 			   int (*iter)(struct nf_conn *i, void *data),
@@ -283,7 +275,7 @@ static inline int nf_ct_is_dying(const struct nf_conn *ct)
 
 static inline int nf_ct_is_untracked(const struct nf_conn *ct)
 {
-	return test_bit(IPS_UNTRACKED_BIT, &ct->status);
+	return false;
 }
 
 /* Packet is received from loopback */
diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h
index 6a8e33dd4ecb..b4a0a1940118 100644
--- a/include/uapi/linux/netfilter/nf_conntrack_common.h
+++ b/include/uapi/linux/netfilter/nf_conntrack_common.h
@@ -28,12 +28,14 @@ enum ip_conntrack_info {
 	/* only for userspace compatibility */
 #ifndef __KERNEL__
 	IP_CT_NEW_REPLY = IP_CT_NUMBER,
+#else
+	IP_CT_UNTRACKED = 7,
 #endif
 };
 
 #define NF_CT_STATE_INVALID_BIT			(1 << 0)
 #define NF_CT_STATE_BIT(ctinfo)			(1 << ((ctinfo) % IP_CT_IS_REPLY + 1))
-#define NF_CT_STATE_UNTRACKED_BIT		(1 << (IP_CT_NUMBER + 1))
+#define NF_CT_STATE_UNTRACKED_BIT		(1 << (IP_CT_UNTRACKED + 1))
 
 /* Bitset representing status of connection. */
 enum ip_conntrack_status {
@@ -94,7 +96,7 @@ enum ip_conntrack_status {
 	IPS_TEMPLATE_BIT = 11,
 	IPS_TEMPLATE = (1 << IPS_TEMPLATE_BIT),
 
-	/* Conntrack is a fake untracked entry */
+	/* Conntrack is a fake untracked entry.  Obsolete and not used anymore */
 	IPS_UNTRACKED_BIT = 12,
 	IPS_UNTRACKED = (1 << IPS_UNTRACKED_BIT),